hippojabe_style_image_generator
- Github: yizhennn/hippojabe-generator
- Docs: https://medium.com/@izzysde
使用 hippojabe 的風格生成卡通畫風圖片
- 模型名稱:hippojabe_style_image_generator
- 基礎模型:基於 runwayml/stable-diffusion-v1-5
- 訓練圖像:小河馬實用貼圖--手繪風
- 微調方法:使用 DreamBooth 方法進行文本到圖像的微調
- 微調做法:只用24張圖複製我妹的畫風 - DreamBooth 微調 Stable Diffusion v1-5 實作教學
模型使用方法:
1. 安裝 diffusers, accelerate, cuda版torch
pip install diffusers, accelerate, torch==2.0.1+cu118 torchvision==0.15.2+cu118 torchaudio==2.0.2+cu118 -f https://download.pytorch.org/whl/cu118/torch_stable.html
2. 生成圖片
from diffusers import DiffusionPipeline
import torch
# 加載模型
pipeline = DiffusionPipeline.from_pretrained("izzysde/hippojabe_style_image_generator")
# 如果有 GPU,將模型移到 CUDA
if torch.cuda.is_available():
pipeline.to("cuda")
else:
pipeline.to("cpu")
# 定義生成圖像的參數
prompt = "show a cute bird in the style of hippojabe" # 用英文寫描述一定要用in the style of hippojabe結尾
num_inference_steps = 100 # 控制生成質量和速度的步驟數
guidance_scale = 9 # 控制生成圖像與文本提示的一致性
# 生成圖片
with torch.no_grad():
image = pipeline(prompt, num_inference_steps=num_inference_steps, guidance_scale=guidance_scale)["images"][0]
# 保存或顯示圖像
image.save("generated_image.png")
image.show()
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for izzysde/hippojabe_style_image_generator
Base model
runwayml/stable-diffusion-v1-5